Comments (4)
You can pass a list of images and place the same number of "<|image|>" in your prompt.
from mplug-owl.
I pass a list of images, say 2 images, and modify the prompt. The image_tensor after preprocess has batch size of 2, while the input_ids has batch size of 1,then I run model.generate(), I do get a result, however the result is wrong. Do I misunderstand?
from mplug-owl.
I pass a list of images, say 2 images, and modify the prompt. The image_tensor after preprocess has batch size of 2, while the input_ids has batch size of 1,then I run model.generate(), I do get a result, however the result is wrong. Do I misunderstand?
Could you provide an example and the incorrect response generated by the owl? Btw, the owl has not been trained on SFT data that includes multiple images. Therefore, it is reasonable to expect that it might fail in some cases.
from mplug-owl.
Here are the two images I passed
the prompt is
'USER: <|image|><|image|>{}\nAnswer the question using a single word or phrase. ASSISTANT:'.format('Does the dog in the first picture have same color with the dog in the second picture?')
the response generated by the owl is 'Yes'
from mplug-owl.
Related Issues (20)
- unable to load model HOT 3
- Encountered flash_attn_2_cuda error while running finetune_lora.sh HOT 1
- cur_input_embeds = torch.cat([cur_input_embeds_1, cur_image_features[0:0], cur_input_embeds_2], dim=0),其中cur_image_features[0:0]表示这是一个没有维度的向量,图像的特征并没有真正加进去 HOT 1
- implementation of pre-training stage
- The Quick Start Code cannot be executed in mPLUG-Owl2 HOT 8
- RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:2 and cuda:0! (when checking argument for argument weight in method wrapper_CUDA__cudnn_convolution)
- The code and detailed implementation of Figure 4 and Figure 5 in the paper mPLUG-Owl2 HOT 1
- Is there model checkpoint for multi-language(mainly chinese) videos?
- 对图像进行坐标检测,生成的bbox是resize成正方形之后的值吗? HOT 5
- file configuration_qwen.py not found HOT 1
- No module named 'mplug_owl2.model.multiway HOT 1
- The updated owl2 based on qwen14b? HOT 1
- other downstream tasks available? Like Visual Reasoning, requires the model to predict whether a sentence describes a pair of images HOT 1
- Cannot run inference
- Issue with gradio webui
- cls_token problem with image. HOT 3
- Zero3 train: Invalidate trace cache @ step 391: expected module 25, but got module 5
- Is there any code for fine-tuning the video model?
- QuickStart Code for mplug_owl2.1 has lots of errors. HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mplug-owl.